About

Harsh Pandya is an experienced Associate Software/Data Engineer at Goldman Sachs with expertise in ETL of real-time data stream, Python Software Development, and Data Analysis. He also has brief experience in physical data modeling for Data warehousing. Harsh is skilled in AWS Cloud Computing and Architecture, running computing clusters of Spark / Hadoop Map-Reduce over AWS for Big Data Processing, and proficient with AWS services like EC2, S3, Lambda, Kinesis, RDS, and Dynamodb. With a relevant experience of 5.02 years, Harsh has a strong background in Machine Learning, including Regression (Linear, Polynomial, Ridge, Lasso), Logistic Regression, Time Series Analysis, SVM, Decision Trees, Random Forest, K- Nearest Neighbour, and Deep Learning - Artificial Neural Networks. He has a GitHub profile with several projects and contributions to open-source projects. Currently, as a Software Engineer (Associate) at Goldman Sachs, Harsh is working on ESG related data curation, data modeling, data quality, and data governance, powering firm-wide critical risk modeling and decision-making. He has previously worked at Gleason Corporation as a Data Scientist, where he developed real-time data pipelines to feed data into ML models and generate predictions in near real-time. Harsh also acted as a point of contact for Data platforms and managing data lakes, scheduled jobs in Airflow and SQL to regularly generate daily insights, data backhauling, and data quality checks. Harsh holds a Master’s Degree in Computer and Information Sciences from Rochester Institute of Technology and a Bachelor’s Degree in Computer Science & Engineering from GTU. His tech stack includes Software Engineer, AWS, Data Engineering, ML, SVM, Python, Random Forest, Azure, ETL, Apache Airflow, Deep Learning, Spark, Data Scientist, Research Scientist, SQL, Big Data, Neural Networks, Hadoop, Databricks, Redis, Kubernetes, and Docker.